Hugo Vergnes personal blog

Training a 3.8B LLM to 0.384 CORE for $998

A 3.8B model pretrained from scratch to 0.384 CORE on 65B tokens in 43 hours, for $998.
Points
121
HN comments
20
Submissions
1
Cited by
0 commenters

AI & Machine LearningSoftware Engineering2026

On Hacker News

SubmittedTitle on HNPointsComments
Sep 10, 2026Training a 3.8B LLM to 0.384 CORE for $998 by Anon8412120

Related posts from the same era